Activation Function of Wavelet Chaotic Neural Networks

摘要：

In this paper, we studied the activation function of chaotic neural network, at first we review Chens chaotic neural network and then propose a novel chaotic neural network model whose activation Junction is compose of sigmoid and wavelet Junction, Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chens and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid.

关键词： Chaotic neural network activation Junction wavelet junction the largest Lyapunov exponents.

作者: Yao-qun Xu Ming Sun Meng-shu Quo

作者单位: Institute of Computer and Information Engineering Harbin University of Commerce 150028, Harbin, Chin Center for Control Theory and Guidance Technology Harbin Institute of Technology 150001, Harbin, Chi

会议类型: 国际会议

会议名称: Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)

会议地点: 北京

会议语种:英文

页码: 716-721

在线出版日期: 2006-07-17（万方平台首次上网日期，不代表论文的发表时间）